huggy_edm_lora_v4 / README.md
linoyts's picture
linoyts HF staff
End of training
2056e2b verified
metadata
tags:
  - stable-diffusion-xl
  - stable-diffusion-xl-diffusers
  - diffusers-training
  - text-to-image
  - diffusers
  - lora
  - template:sd-lora
widget:
  - text: a <s0><s1> emoji dressed as yoda
    output:
      url: image_0.png
  - text: a <s0><s1> emoji dressed as yoda
    output:
      url: image_1.png
  - text: a <s0><s1> emoji dressed as yoda
    output:
      url: image_2.png
  - text: a <s0><s1> emoji dressed as yoda
    output:
      url: image_3.png
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: a <s0><s1> emoji
license: openrail++

SDXL LoRA DreamBooth - linoyts/huggy_edm_lora_v4

Prompt
a <s0><s1> emoji dressed as yoda
Prompt
a <s0><s1> emoji dressed as yoda
Prompt
a <s0><s1> emoji dressed as yoda
Prompt
a <s0><s1> emoji dressed as yoda

Model description

These are linoyts/huggy_edm_lora_v4 LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.

Download model

Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke

Use it with the 🧨 diffusers library

from diffusers import AutoPipelineForText2Image
import torch
from huggingface_hub import hf_hub_download
from safetensors.torch import load_file
        
pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('linoyts/huggy_edm_lora_v4', weight_name='pytorch_lora_weights.safetensors')
embedding_path = hf_hub_download(repo_id='linoyts/huggy_edm_lora_v4', filename='huggy_edm_lora_v4_emb.safetensors', repo_type="model")
state_dict = load_file(embedding_path)
pipeline.load_textual_inversion(state_dict["clip_l"], token=["<s0>", "<s1>"], text_encoder=pipeline.text_encoder, tokenizer=pipeline.tokenizer)
pipeline.load_textual_inversion(state_dict["clip_g"], token=["<s0>", "<s1>"], text_encoder=pipeline.text_encoder_2, tokenizer=pipeline.tokenizer_2)
        
image = pipeline('a <s0><s1> emoji dressed as yoda').images[0]

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers

Trigger words

To trigger image generation of trained concept(or concepts) replace each concept identifier in you prompt with the new inserted tokens:

to trigger concept TOK → use <s0><s1> in your prompt

Details

All Files & versions.

The weights were trained using 🧨 diffusers Advanced Dreambooth Training Script.

LoRA for the text encoder was enabled. False.

Pivotal tuning was enabled: True.

Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.